Full identifiability of independent mechanism analysis
Establish whether independent mechanism analysis, which constrains the columns of the Jacobian of a nonlinear mixing diffeomorphism to be orthogonal without using an observed auxiliary variable, delivers full identifiability.
References
It is not, however, known to deliver full identifiability on its own.
— Foundations of Independent Component Analysis
(2608.13229 - Forré, 13 Aug 2026) in Section 7.6, paragraph “Relaxing linearity”
Which of these recovers individual latents, and under what condition on the observation map, is an open question, which we leave to future work, along with the joint diagonalization baseline sketched earlier in this paragraph.
— DSReg: Provably Recovering Individual World Latents without Reconstruction
(2610.09457 - Zheng et al., 7 Oct 2026) in Appendix, Section 'Additional discussions', paragraph 'Independent mechanism analysis'